Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2134 in Layer 5
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 1.5400. Min Range: -1.5400
Max Act: 1.5400. Min Act: -0.1699
Data Index: 8565123 (Open Web Text)
Max Activating Token Index: 628
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 1.5400. Min Range: -1.5400
Max Act: 1.4698. Min Act: -0.1700
Data Index: 7257721 (Open Web Text)
Max Activating Token Index: 658
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 1.5400. Min Range: -1.5400
Max Act: 1.4698. Min Act: -0.1699
Data Index: 24935 (Open Web Text)
Max Activating Token Index: 265
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 1.5400. Min Range: -1.5400
Max Act: 1.4698. Min Act: -0.1698
Data Index: 3229587 (Open Web Text)
Max Activating Token Index: 348
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 1.5400. Min Range: -1.5400
Max Act: 1.4522. Min Act: -0.1700
Data Index: 3310174 (Open Web Text)
Max Activating Token Index: 267
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 1.5400. Min Range: -1.5400
Max Act: 1.3994. Min Act: -0.1700
Data Index: 567497 (Open Web Text)
Max Activating Token Index: 472
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 1.5400. Min Range: -1.5400
Max Act: 1.3994. Min Act: -0.1670
Data Index: 1357915 (Open Web Text)
Max Activating Token Index: 535
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 1.5400. Min Range: -1.5400
Max Act: 1.3642. Min Act: -0.1656
Data Index: 7592255 (Open Web Text)
Max Activating Token Index: 287
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 1.5400. Min Range: -1.5400
Max Act: 1.3642. Min Act: -0.1700
Data Index: 4446816 (Open Web Text)
Max Activating Token Index: 65
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 1.5400. Min Range: -1.5400
Max Act: 1.3642. Min Act: -0.1700
Data Index: 4571510 (Open Web Text)
Max Activating Token Index: 429
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 1.5400. Min Range: -1.5400
Max Act: 1.3642. Min Act: -0.1700
Data Index: 4241266 (Open Web Text)
Max Activating Token Index: 432
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 1.5400. Min Range: -1.5400
Max Act: 1.3289. Min Act: -0.1700
Data Index: 2259567 (Open Web Text)
Max Activating Token Index: 641
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 1.5400. Min Range: -1.5400
Max Act: 1.3112. Min Act: -0.1700
Data Index: 1912097 (Open Web Text)
Max Activating Token Index: 860
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 1.5400. Min Range: -1.5400
Max Act: 1.3112. Min Act: -0.1700
Data Index: 3145662 (Open Web Text)
Max Activating Token Index: 399
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 1.5400. Min Range: -1.5400
Max Act: 1.2936. Min Act: -0.1700
Data Index: 3973006 (Open Web Text)
Max Activating Token Index: 560
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 1.5400. Min Range: -1.5400
Max Act: 1.2936. Min Act: -0.1700
Data Index: 973724 (Open Web Text)
Max Activating Token Index: 181
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 1.5400. Min Range: -1.5400
Max Act: 1.2936. Min Act: -0.1692
Data Index: 1335609 (Open Web Text)
Max Activating Token Index: 335
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 1.5400. Min Range: -1.5400
Max Act: 1.2936. Min Act: -0.1700
Data Index: 5680734 (Open Web Text)
Max Activating Token Index: 742
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 1.5400. Min Range: -1.5400
Max Act: 1.2936. Min Act: -0.1685
Data Index: 6520720 (Open Web Text)
Max Activating Token Index: 968
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 1.5400. Min Range: -1.5400
Max Act: 1.2583. Min Act: -0.1700
Data Index: 2868133 (Open Web Text)
Max Activating Token Index: 345
Click toggle to see full text
Truncated
Full Text #19